Experienced coders and people who have never done so much as a "Hello World" exercise are all having a blast with vibe coding. That's the practice of telling an AI model in plain English what software you want to make and then watching it rattle off lines of code faster than you can read them.

I run Home Assistant in Proxmox on my mini PC, along with multiple other services. I use local LLMs running in Ollama, but they're very slow on my local hardware. I've always wanted to use a local LLM to make my local voice assistant smarter, but until now, it's always been far too slow or inaccurate to be of any use.

Your private chats with Anthropic's Claude might be very public. Searchers have discovered that many Claude conversations are searchable in Google, some of them containing sensitive information.

I use local LLMs on a daily basis, but in my personal setup, they're only really useful for a limited selection of tasks. I wanted to see how a local LLM could handle everyday tasks. My most powerful device for running LLMs is my M2 MacBook Air with only 8GB of RAM, so while more powerful hardware could do much more, these results should broadly match what you can do on similar hardware.

Back in April, OpenAI released Computer Use as a feature of Codex. I've used it quite a few times over the past handful of months, and it's actually so much more useful than I ever thought it would be.

Most people who use AI assistants spend more time switching windows than they think. You copy something, alt+tab to a browser, open a chat window, paste it in, wait, copy the response, and tab back to wherever you were. If you do that twenty times a day, you're losing more time to that routine than to the actual problem you're trying to solve. Wiring your Windows clipboard directly to Claude's API will help you out.

What I want from AI is for it to take the boring and mundane jobs off my hands and free me up to do more fun stuff. Reading my emails before starting work each day is time-consuming and dull, so I decided to hand the task off to Claude.

Large language models (LLMs) might be the most accessible and flexible technology we've ever had access to. By default, they're presented as chatbots—but that's just one way to interact with them. With the right prompts, you can transform an LLM into something that behaves like an entirely different app, complete with its own custom interface.